© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16589
    Prev
    Next
    INDEX
    Explanations

    political systems and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    benen
    -0.06
     rtl
    -0.06
    ðŁĺĢ
    -0.06
     lessen
    -0.06
     herrer
    -0.06
     Polda
    -0.06
     exager
    -0.06
     racked
    -0.06
    ï¿
    -0.06
    eken
    -0.06
    POSITIVE LOGITS
    åħī顾
    0.06
    ä¸İæľ¬
    0.06
     sw
    0.06
    å½ĵåħ¶
    0.06
    æľīå¦Ĥ
    0.06
    æľ¬äººèº«ä»½è¯ģ
    0.05
    ench
    0.05
     dy
    0.05
    ephy
    0.05
    å¦Ĥåħ¶
    0.05
    Activations Density 0.021%

    No Known Activations